initial model commit

README.md

@@ -0,0 +1,151 @@
+---
+tags:
+- flair
+- token-classification
+- sequence-tagger-model
+language: en
+datasets:
+- conll2000
+inference: false
+---
+
+## English Chunking in Flair (fast model)
+
+This is the fast phrase chunking model for English that ships with [Flair](https://github.com/flairNLP/flair/).
+
+F1-Score: **96,48** (corrected CoNLL-2000)
+
+Predicts 4 tags:
+
+| **tag**                        | **meaning** |
+|---------------------------------|-----------|
+| ADJP     | adjectival |
+| ADVP     | adverbial |
+| CONJP     | conjunction |
+| INTJ     | interjection |
+| LST     | list marker |
+| NP     | noun phrase |
+| PP     | prepositional |
+| PRT     | particle |
+| SBAR      | subordinate clause |
+| VP      | verb phrase |
+
+Based on [Flair embeddings](https://www.aclweb.org/anthology/C18-1139/) and LSTM-CRF.
+
+---
+
+### Demo: How to use in Flair
+
+Requires: **[Flair](https://github.com/flairNLP/flair/)** (`pip install flair`)
+
+```python
+from flair.data import Sentence
+from flair.models import SequenceTagger
+
+# load tagger
+tagger = SequenceTagger.load("flair/chunk-english")
+
+# make example sentence
+sentence = Sentence("The happy man has been eating at the diner")
+
+# predict NER tags
+tagger.predict(sentence)
+
+# print sentence
+print(sentence)
+
+# print predicted NER spans
+print('The following NER tags are found:')
+# iterate over entities and print
+for entity in sentence.get_spans('np'):
+    print(entity)
+
+```
+
+This yields the following output:
+```
+Span [1,2,3]: "The happy man"   [− Labels: NP (0.9958)]
+Span [4,5,6]: "has been eating"   [− Labels: VP (0.8759)]
+Span [7]: "at"   [− Labels: PP (1.0)]
+Span [8,9]: "the diner"   [− Labels: NP (0.9991)]
+
+```
+
+So, the spans "*The happy man*" and "*the diner*" are labeled as **noun phrases** (NP) and "*has been eating*" is labeled as a **verb phrase** (VP) in the sentence "*The happy man has been eating at the diner*". 
+
+
+---
+
+### Training: Script to train this model
+
+The following Flair script was used to train this model: 
+
+```python
+from flair.data import Corpus
+from flair.datasets import CONLL_2000
+from flair.embeddings import WordEmbeddings, StackedEmbeddings, FlairEmbeddings
+
+# 1. get the corpus
+corpus: Corpus = CONLL_2000()
+
+# 2. what tag do we want to predict?
+tag_type = 'np'
+
+# 3. make the tag dictionary from the corpus
+tag_dictionary = corpus.make_tag_dictionary(tag_type=tag_type)
+
+# 4. initialize each embedding we use
+embedding_types = [
+
+    # contextual string embeddings, forward
+    FlairEmbeddings('news-forward'),
+
+    # contextual string embeddings, backward
+    FlairEmbeddings('news-backward'),
+]
+
+# embedding stack consists of Flair and GloVe embeddings
+embeddings = StackedEmbeddings(embeddings=embedding_types)
+
+# 5. initialize sequence tagger
+from flair.models import SequenceTagger
+
+tagger = SequenceTagger(hidden_size=256,
+                        embeddings=embeddings,
+                        tag_dictionary=tag_dictionary,
+                        tag_type=tag_type)
+
+# 6. initialize trainer
+from flair.trainers import ModelTrainer
+
+trainer = ModelTrainer(tagger, corpus)
+
+# 7. run training
+trainer.train('resources/taggers/chunk-english',
+              train_with_dev=True,
+              max_epochs=150)
+```
+
+
+
+---
+
+### Cite
+
+Please cite the following paper when using this model.
+
+```
+@inproceedings{akbik2018coling,
+  title={Contextual String Embeddings for Sequence Labeling},
+  author={Akbik, Alan and Blythe, Duncan and Vollgraf, Roland},
+  booktitle = {{COLING} 2018, 27th International Conference on Computational Linguistics},
+  pages     = {1638--1649},
+  year      = {2018}
+}
+```
+
+---
+
+### Issues?
+
+The Flair issue tracker is available [here](https://github.com/flairNLP/flair/issues/).

loss.tsv

@@ -0,0 +1,132 @@
+EPOCH	TIMESTAMP	BAD_EPOCHS	LEARNING_RATE	TRAIN_LOSS
+0	05:21:01	0	0.1000	17.34242542215756
+1	05:22:04	0	0.1000	5.6257953405380245
+2	05:23:06	0	0.1000	4.303623300790787
+3	05:24:08	0	0.1000	3.684522943837302
+4	05:25:10	0	0.1000	3.3204722804682594
+5	05:26:13	0	0.1000	3.0727916134255273
+6	05:27:16	0	0.1000	2.84662518118109
+7	05:28:18	0	0.1000	2.7059059996690067
+8	05:29:21	0	0.1000	2.5761325248650144
+9	05:30:23	0	0.1000	2.440997558406421
+10	05:31:25	0	0.1000	2.3059833283935274
+11	05:32:25	0	0.1000	2.255575483611652
+12	05:33:26	0	0.1000	2.160707050561905
+13	05:34:28	0	0.1000	2.1140442326664926
+14	05:35:30	0	0.1000	2.010098801766123
+15	05:36:33	0	0.1000	1.9878978673900878
+16	05:37:35	0	0.1000	1.9592591504965509
+17	05:38:36	0	0.1000	1.8743698948196001
+18	05:39:38	0	0.1000	1.8482042870351247
+19	05:40:40	0	0.1000	1.8149086647800037
+20	05:41:41	1	0.1000	1.844334631732532
+21	05:42:42	0	0.1000	1.764170822075435
+22	05:43:44	0	0.1000	1.7315230512193271
+23	05:44:46	0	0.1000	1.636917947445597
+24	05:45:48	1	0.1000	1.6695456045014518
+25	05:46:50	2	0.1000	1.651555403641292
+26	05:47:52	0	0.1000	1.6244623371532985
+27	05:48:54	0	0.1000	1.5596783099429947
+28	05:49:56	0	0.1000	1.514996995457581
+29	05:50:58	0	0.1000	1.5029920841966355
+30	05:52:00	0	0.1000	1.431032625905105
+31	05:53:01	1	0.1000	1.4837342532617706
+32	05:54:03	2	0.1000	1.4580539977976255
+33	05:55:05	3	0.1000	1.4399318626948765
+34	05:56:07	4	0.1000	1.4475846835545132
+35	05:57:09	0	0.0500	1.2653039670416286
+36	05:58:11	0	0.0500	1.235799746428217
+37	05:59:13	1	0.0500	1.2381288805178234
+38	06:00:15	0	0.0500	1.2142414430422441
+39	06:01:16	0	0.0500	1.1662018648215702
+40	06:02:17	1	0.0500	1.19737099728414
+41	06:03:19	2	0.0500	1.1784159956233842
+42	06:04:20	0	0.0500	1.136076490368162
+43	06:05:21	1	0.0500	1.1422300245080674
+44	06:06:23	0	0.0500	1.1005895431552615
+45	06:07:24	0	0.0500	1.0893675114427295
+46	06:08:26	1	0.0500	1.115694132979427
+47	06:09:28	2	0.0500	1.1003576530941894
+48	06:10:31	0	0.0500	1.0747537553310393
+49	06:11:34	1	0.0500	1.093895332302366
+50	06:12:37	0	0.0500	1.045550647271531
+51	06:13:39	0	0.0500	1.0378333334411893
+52	06:14:43	1	0.0500	1.052635036621775
+53	06:15:46	2	0.0500	1.0383459685104235
+54	06:16:48	3	0.0500	1.0617959085319724
+55	06:17:51	0	0.0500	1.0143299671156065
+56	06:18:54	1	0.0500	1.0251009391886847
+57	06:19:55	0	0.0500	0.9945888205298355
+58	06:20:56	0	0.0500	0.9834732017346791
+59	06:21:58	0	0.0500	0.9683706868972097
+60	06:23:00	1	0.0500	1.0107239616768702
+61	06:24:03	0	0.0500	0.9520225398242473
+62	06:25:06	1	0.0500	0.9631213486194611
+63	06:26:08	0	0.0500	0.9376531612660204
+64	06:27:10	1	0.0500	0.9862911478749343
+65	06:28:10	2	0.0500	0.9777858261551176
+66	06:29:11	3	0.0500	0.9611380408917155
+67	06:30:11	4	0.0500	0.9442767329514027
+68	06:31:12	0	0.0250	0.8669117001550538
+69	06:32:13	1	0.0250	0.9229169498596873
+70	06:33:15	2	0.0250	0.8993198933345931
+71	06:34:16	3	0.0250	0.880038060354335
+72	06:35:17	0	0.0250	0.8603246239147015
+73	06:36:18	1	0.0250	0.8772120903645243
+74	06:37:21	0	0.0250	0.8479232568825994
+75	06:38:23	0	0.0250	0.7854352353938988
+76	06:39:24	1	0.0250	0.8638150128935065
+77	06:40:24	2	0.0250	0.8433980496866362
+78	06:41:25	3	0.0250	0.8262564968849931
+79	06:42:26	4	0.0250	0.8527375097785678
+80	06:43:27	1	0.0125	0.8060048690864018
+81	06:44:29	0	0.0125	0.7787820570170879
+82	06:45:30	1	0.0125	0.8047857295189585
+83	06:46:30	2	0.0125	0.8353619445647512
+84	06:47:31	3	0.0125	0.7827996164560318
+85	06:48:32	4	0.0125	0.7826738729008607
+86	06:49:33	1	0.0063	0.7854060885097299
+87	06:50:34	0	0.0063	0.7773133634456566
+88	06:51:35	1	0.0063	0.7824090438229697
+89	06:52:35	0	0.0063	0.7511799194983073
+90	06:53:36	1	0.0063	0.7688422220093863
+91	06:54:36	2	0.0063	0.7514194880213056
+92	06:55:37	0	0.0063	0.7506189524063043
+93	06:56:37	1	0.0063	0.7805234477988311
+94	06:57:38	2	0.0063	0.7742435120046138
+95	06:58:38	3	0.0063	0.7982145274324076
+96	06:59:38	4	0.0063	0.7590283545000213
+97	07:00:39	0	0.0031	0.7236002066305706
+98	07:01:40	1	0.0031	0.7341974345701081
+99	07:02:41	2	0.0031	0.7550298560942922
+100	07:03:41	0	0.0031	0.712286435599838
+101	07:04:43	1	0.0031	0.7448591279132025
+102	07:05:44	2	0.0031	0.7522817966129098
+103	07:06:45	3	0.0031	0.7498979801578182
+104	07:07:46	4	0.0031	0.769592082287584
+105	07:08:46	1	0.0016	0.7390777413334165
+106	07:09:47	0	0.0016	0.7049496266458716
+107	07:10:48	1	0.0016	0.7368284867278168
+108	07:11:48	2	0.0016	0.7685823498027665
+109	07:12:50	3	0.0016	0.7776820374386652
+110	07:13:52	4	0.0016	0.7452258818915912
+111	07:14:53	1	0.0008	0.7270229106502873
+112	07:15:54	2	0.0008	0.7077597582978862
+113	07:16:56	0	0.0008	0.7014804634132555
+114	07:17:57	1	0.0008	0.7204148694872856
+115	07:18:58	0	0.0008	0.6946687193853515
+116	07:19:58	1	0.0008	0.7694109963519232
+117	07:20:59	2	0.0008	0.7071356939417975
+118	07:22:00	3	0.0008	0.759676700511149
+119	07:23:01	4	0.0008	0.771170526849372
+120	07:24:03	1	0.0004	0.7428989289062363
+121	07:25:05	2	0.0004	0.7075921507818358
+122	07:26:06	3	0.0004	0.7152813235563892
+123	07:27:08	4	0.0004	0.709876735402005
+124	07:28:10	1	0.0002	0.7386109314858913
+125	07:29:12	2	0.0002	0.731379884587867
+126	07:30:14	0	0.0002	0.6848466526184763
+127	07:31:16	1	0.0002	0.7517304641859872
+128	07:32:17	2	0.0002	0.7443433770111629
+129	07:33:17	3	0.0002	0.7162831548069205
+130	07:34:19	4	0.0002	0.7369625336357526

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:359acc17acefa7b5d45dfb6b9cad5a3292c3f6bfef402a10f2042d50f41b845f
+size 75233247